Measured persona prompt templates and contrastive persona pairs for steering experiments
Updated 2026-06-25 14:08:19 +08:00
Hypothesis: you can distill a steering vector into LoRA weights and "heal" the incoherency the vector injects by regularising the training (KL to base, or weight decay). Then loop and see what multiple rounds give you.
Updated 2026-06-24 20:50:29 +08:00
Updated 2026-06-01 14:30:20 +08:00
Updated 2026-05-13 10:46:52 +08:00
Updated 2026-05-05 08:12:41 +08:00
Updated 2026-04-05 07:04:52 +08:00
HTML tables from pandas DataFrames
Updated 2026-02-27 16:36:41 +08:00
Robust recipes to align language models with human and AI preferences
Updated 2025-06-04 13:37:07 +08:00
Updated 2025-04-27 15:37:14 +08:00
A basic editor for xBrowserSync json backup files
Updated 2024-11-09 10:49:53 +08:00
Implementation of Dreamer v3 in pytorch.
Updated 2024-06-08 11:04:39 +08:00
A langchain app to visualise a debate using Tree-of-Thought reasoning
Updated 2024-02-25 09:22:14 +08:00
Updated 2023-04-22 20:03:16 +08:00